Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/treex-x/workflowx/claude-mdgit clone --depth 1 https://github.com/TreeX-X/WorkFlowXWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
WorkFlowX CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - WorkflowX Instructions
You are the Main Agent. Responsibilities: direct execution, optional native parallel coordination, routing, design, and Hybrid Tree management when required.
Capabilities: native reasoning, optional Hybrid Tree management, and native Agent coordination.
Routing
Full specification:
.claude/skills/orchestrateX/SKILL.mdExecution rule:
xdois direct work by the Main Agent and does not require a dispatch harness. Native parallel Agents are used only when the user explicitly requests parallel development.xdeldelegates one Hybrid Tree task to coderX with self-review and no evaluatorX;xflowuses module 08 repository discovery, stage-batched socratesX clarification, and one Ready Summary confirmation before the full planning/evaluation workflow.
Routing and mode recommendation are defined in .claude/skills/orchestrateX/SKILL.md.
Orchestrator Workflow
Full specification:
.claude/skills/orchestrateX/SKILL.md
| Mode | Command | Behavior |
|---|---|---|
xflow |
/xflow [-box] [-parallel] [-team] |
Full planning -> Hybrid Tree -> implementation -> evaluation |
xdel |
/xdel <requirement or Hybrid Tree> |
Hybrid Tree-backed one-shot coderX delegation with self-review |
xdo |
/xdo [--parallel] <requirement> |
Main Agent direct work; parallel only when explicitly requested |
Agent dispatch:
Agent({ subagent_type: "coderX", isolation: "worktree", prompt: "<Dispatch Payload: coderX Task>" })
Agent({ subagent_type: "evaluatorX", isolation: "worktree", prompt: "..." })
Before dispatching coderX, Main Agent must assemble the Dispatch Payload: coderX Task defined in .claude/skills/orchestrateX/modules/02-bus-payload.md, including Execution Brief, Context Manifest, and Context Budget. Do not send vague implementation prompts to coderX.
Before dispatching evaluatorX, Main Agent must assemble the Dispatch Payload: evaluatorX Review Task defined in .claude/skills/orchestrateX/modules/02-bus-payload.md, including Review Brief, Review Context Manifest, and Review Context Budget. Do not send vague review prompts to evaluatorX.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 62 lines · 803 tokens per session scan A 801fc721f9e6
WorkFlowX CLAUDE.md is an instructions file published in the GitHub repository TreeX-X/WorkFlowX (55 stars, last pushed 2d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
usurahi CLAUDE.md
Instructions for usurahi-project/usurahi, covering 薄氷（うすらひ）— 共通ガイド, 薄氷とは, 共通原則, 会議状態の最小定義 and 起動時.
good-bad-ugly AGENTS.md
AGENTS.md instructions for XyndoX/good-bad-ugly, covering good-bad-ugly — tiered multi-agent orchestration, tiers, the loop, big features: spec → plan → execute and external-system discipline.
AI-System-Design-Consultant CLAUDE.md
Instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.
agent-eve CLAUDE.md
Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).
team-shinchan AGENTS.md
Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.
coordinate-agents AGENTS.md
Instructions for hogancv/coordinate-agents, covering repository instructions for ai contributors, canonical identity, repository map, required checks and change rules.